Mutual Modality Learning for Video Action Classification
This work addresses the computational expense of using multiple modalities during inference in video action classification, offering an incremental improvement for researchers and practitioners in computer vision.
The paper tackled the problem of improving video action classification by integrating multi-modality ensemble advantages into a single RGB model to reduce computational costs, achieving state-of-the-art results on the Something-Something-v2 benchmark.
The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different modalities (e.g. Optical flow). Unfortunately, it is computationally expensive to use several modalities during inference. Recent works examine the ways to integrate advantages of multi-modality into a single RGB-model. Yet, there is still a room for improvement. In this paper, we explore the various methods to embed the ensemble power into a single model. We show that proper initialization, as well as mutual modality learning, enhances single-modality models. As a result, we achieve state-of-the-art results in the Something-Something-v2 benchmark.